Enhanced Feature-Based Automatic Text Summarization SystemUsingSupervised Technique
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2016, Vol 15, Issue 5
Abstract
In this work, we propose an efficient text summarization methodby ranking sentences according to their scores that use a combination of existing and improved sentence features. Many works in the literature proposed improvements to text summarization but this field still needs more improvement. For this purpose, we propose improvements to Sentence position, Sentence length, and Key wordsentence features. Afterwards, we find the optimal combination between these features and some existing features such as Term frequency, Sentence centrality, Title similarity, and Upper case of word. By usingmachine learning techniques, mainly SVM, Naive Bayes and Decision Tree classifiersour paper evaluates two feature groups: a combination of seven features without any improvements,and the same seven features after making some improvements onSentence position, Sentence length, and Key word sentence features to enhance the performance of text summarization system.Experimental results showed that making enhancements on some features improved the accuracy.
Authors and Affiliations
Madhi Ahmed Ali, Ali A. Al-Dahoud, Bilal H. Hawashin
Keywords
Related Articles
- EP ID EP650832
- DOI 10.24297/ijct.v15i5.1630
- Views 86
- Downloads 0
Advanced IT Outsourcing By Using Cloud Computing Model
In this paper we will discuss Outsourcing is the commissioning of a third party (or a number of third parties) to manage a client organization.s IT assets, people and/ or activities to required results. Business process...
Role of Biometric security for The Enhancement of Data Security
In today's society, data security is the big problem for every business organization or an individual. Most found threat is theft of personal data and information. With time digital data become more prevalent, personnel...
Evaluating a Model for Implementing Knowledge Management in Banking Informatics Corporations in Iran
The purpose of this paper is to measure the perceived importance and practical establishment of five factors affecting successful establishment of knowledge management (KM) in banking informatics corporations in Iran bas...
Fangled Protocol for Black Hole Detection in Ad Hoc Networks
Now a day, security in Mobile Ad hoc Network is very important issue. Due to dynamic topology and mobility of nodes, Mobile Ad hoc Networks are more vulnerable to security attacks than conventional wired and wireless net...
History Aware Anomaly Based IDS for Cloud IaaS
Cloud Computing provides different types of services such as SaaS, PaaS, IaaS. Each of them have their own security challenges, but IaaS undertakes all types of challenges viz., network attack ,behaviour based attack,...